The demand for bandwidth-critical applications has stimulated the research community not only to develop new ways of communication, but also to use the existing spectrum efficiently. Networks have become dynamic and heterogeneous. Receivers have received various signals that can be modulated differently. Automatic modulation classification (AMC) is a key procedure for present and next-generation communication networks, and facilitates the demodulation process at the receiver side. Under the presence of noise from the channel, the transmitter and receiver with its unknown parameters, such as carrier frequency, phase offset, signal power, and timing information, have become cumbersome because detecting the modulation scheme of the received signal is a complicated procedure. Two main methods, namely maximum likelihood functions and the signal statistical feature-based (FB) approach, are used for the automatic classification of modulated signals. In this study, a comprehensive survey of various modulation techniques based on FB approach is conducted. In this research, a number of basic features that are usually used in determining and discriminating modulation types were investigated. The classifier that was used in the discrimination process is studied in detail and compared to other types of classifiers to help the reader determine the limitations associated with the FB approach. Both classifiers and basic features were compared, and their advantages and disadvantages were investigated based on previous researches to determine the best type of classifier and the set of features in relation to each discrimination environment. This work serves as a guide for researchers of AMC to determine the suitable features and algorithms.

Most psychologists argue that facial behavioral during lying is different from facial behavioral when telling the truth, so the facial behavioral can be used as reliable indicators for spotting liars. The deception detection systems (DDSs) based on facial expressions are non-invasive, mobile and cost-effective. In this work a DDS is dependent on Facial Action Coding System (FACS) for facial features extraction, the main idea of FACS is to describe all facial actions using Action Units (AUs), each AU is related to movement one or more facial muscles. Eight AUs are used which incorporated into a single facial behavior pattern vector; these AUs are AUs 5, 6, 7, 10, 12, 14, 23, and 28. Datasets are collected for 43 subjects (20males, 23 females) most of them between ages 18-25. Four types of classification algorithms are used individually in the last stage of the proposed system; these classifiers are MLP, KNN, VG-RAM, and SVM. The simulation results show that the best results are obtaining when using VG-RAM and KNN classifiers. The main contributions of this work are new classification techniques in DDS, collect real database that can use to measure the performance of any DDS based on facial expressions, and select suitable facial features.

This paper presents a diagnosis system design used to assist the physicians to diagnose the heart condition by converting medical factors of the patients into a numerical representation. The proposed heart disease diagnosis system can classify two heart conditions (normal and abnormal). Also, it can classify four abnormality heart conditions in addition to the normal case. Two types of database are used in the classification process: the online database from The University of California, Irvine (UCI) machine learning dataset repository and collected real database (CD). These databases consist of 13 medical factors that are successful in diagnosing heart disease. The simulation results show that, the proposed Numeral Virtual Generalizing Random Access Memory (NVG-RAM) Weightless Neural Network classifier has 100% accuracy of two heart diseases classification when the performance of this classifier was evaluated using CD. Additionally, this classifier achieves 90% success rate when recognizing 5 states for the same database. According to the UCI database the NVG-RAM is considered best classifier for classifying two types of heart disease based on different division of training and testing database. Furthermore, the diagnosis accuracy for classifying five types is 71.698%. The proposed Heart disease classifier is hardware implemented using FPGA platform kit (Spartan-3A DSP 3400A). This classifier achieves high success rate when tested in using CD for diagnosis two-class heart disease that gives maximum accuracy 100%. Moreover, the NVG-RAM is considered a good algorithm to diagnosis multiclass heart diseases that gives a maximum accuracy of 88%.

Detection of eye gaze direction is a hot topic for research in the computer vision area which can be used in many applications. Although significant eye tracking techniques have been presented by the researchers for the last years, it is still the challenging task for improving the performance of the gaze detection system. This paper presents a new eye feature extraction system to build a robust eye gaze classier which uses the Viola-Jones algorithm to face detection and Constrained Local Neural Field model for eye region localization. Furthermore, geometry features of the eye are extracted from the detected eye region based on angles of a triangle of the eye. The algorithms were tested by a new dataset created from 34 participant females and males in different ages. The experimental results show that this method has better features extraction for the classification process.